Join us to pioneer enterprise-grade Generative AI applications, leveraging the power of Large Language Models (LLMs). This role focuses on developing advanced solutions that drive innovation and address complex business challenges.

We are committed to your growth, offering diverse career paths and internal mobility within the Capgemini group. You'll benefit from comprehensive wellness programs, including health checks, telemedicine, robust insurance options, and support for elder care and new parents, alongside flexible work arrangements.

Design and implement scalable Generative AI applications utilizing LLMs. Build and refine Retrieval-Augmented Generation (RAG) systems for enhanced data retrieval. Develop sophisticated AI agents and multi-agent workflows using leading frameworks like LangChain, LangGraph, Semantic Kernel, AutoGen, or CrewAI. Seamlessly integrate AI models with existing enterprise systems, APIs, databases, and knowledge repositories. Fine-tune, meticulously evaluate, and optimize foundation models to meet specific business needs.

A strong foundation in working with advanced LLMs such as OpenAI GPT, Azure OpenAI, Claude, Gemini, Llama, or Mistral is essential. Expertise in Prompt Engineering and Context Engineering techniques is crucial for effective model interaction. Practical experience with RAG pipelines and vector databases is required. Proficiency in fine-tuning, model evaluation, and inference optimization is expected. A solid understanding of AI guardrails, hallucination mitigation, and responsible AI practices is necessary.